def test_parse_motifs(self):
motifs = parse_motifs(os.path.join(Test.__path__[0], "data", "motifs.txt"))
self.assertDictEqual({
'C/VI': (389, 402),
'D': (405, 429),
'F/I-II': (180, 206),
'E/VII': (430, 446),
'B/V': (335, 355),
'A/IV': (259, 270),
'Priming Loop': (519, 538)
},
motifs["WNV"])
def test_calc_prot_drug_contacts_per_motif(self):
contacts_per_cluster, _ = histogram.parse_contacts(TestDataManaging.small_contacts_file_name)
motifs = parse_motifs(os.path.join(Test.__path__[0], "data", "motifs.txt"))
ordered_motifs = ['F/I-II', 'A/IV', 'B/V', 'C/VI', 'D', 'E/VII', 'Priming Loop']
prot_drug_contacts_per_motif = calc_contacts_per_cluster_per_motif(contacts_per_cluster,
motifs["WNV"],
ordered_motifs,
1.)
correct_prot_drug_contacts_per_motif = {
'cluster_8': {'F/I-II': 4.0, 'B/V': 2.0},
'cluster_6': {'A/IV': 2.0, 'B/V': 4.0, 'Priming Loop': 4.0},
'cluster_7': {'A/IV': 15.0, 'Priming Loop': 1.0},
'cluster_4': {'C/VI': 6.0, 'Priming Loop': 4.0, 'B/V': 6.0},
'cluster_5': {'E/VII': 6.0},
'cluster_2': {'C/VI': 4.0, 'D': 5.0, 'Priming Loop': 3.0},
'cluster_3': {'Priming Loop': 6.0, 'B/V': 7.0},
'cluster_0': {'C/VI': 7.0, 'E/VII': 7.0, 'Priming Loop': 2.0},
'cluster_1': {'E/VII': 2.0, 'A/IV': 10.0, 'Priming Loop': 1.0, 'D': 2.0}
}
self.assertDictEqual(correct_prot_drug_contacts_per_motif, prot_drug_contacts_per_motif)
correct_contacts_per_motif = {
'F/I-II': 4.,
'A/IV': 27.,
'B/V': 19.,
'C/VI': 17.,
'D': 7.,
'E/VII': 15.,
'Priming Loop': 21.
}
contacts_per_motif = calc_contacts_per_motif(correct_prot_drug_contacts_per_motif, ordered_motifs)
self.assertDictEqual(correct_contacts_per_motif,contacts_per_motif)
parser.add_option("--results", dest="results")
parser.add_option("--drug-atoms", dest="drug_atoms")
parser.add_option("--frames-per-drug", dest="frames_per_drug")
(options, args) = parser.parse_args()
check_options(options)
tools.create_dir(options.results)
THRESHOLD = 1000
# Parse all files
num_atoms_per_drug = parse_drug_info(options.drug_atoms)
frames_per_prot_drug = parse_frames_info(options.frames_per_drug)
data, proteins, drugs = parse_contacts_file(options.contacts)
motifs = parse_motifs(options.motifs)
# Override order for stuff
ordered_motifs = ['F/I-II', 'A/IV', 'B/V', 'C/VI', 'D', 'E/VII', 'Priming Loop']
drugs.sort()
proteins = ["JEV", "WNV", "TBEV", "BVDV", "HCV", "Polio"]
# PLOT TOTAL NUMBER OF CONTACTS PER PROTEIN
t_c_p_d = get_total_contacts_per_protein_and_drug(data["contacts_per_residue"],
proteins, drugs,
num_atoms_per_drug, frames_per_prot_drug)
db = pd.DataFrame.from_dict(t_c_p_d)
sns.barplot(x="Protein", y="Contacts", hue="Drug", data = db)
plt.savefig(os.path.join(options.results, "total_contacts.svg"))
# PLOT CONTACTS PER RESIDUE
'''
Created on Dec 10, 2015
@author: victor
'''
from prody.proteins.pdbfile import parsePDB, writePDB
import sys
from histogram import parse_motifs
import urllib
if __name__ == '__main__':
pdb = parsePDB(sys.argv[1])
motifs = parse_motifs(sys.argv[2])
prot_name = sys.argv[3]
for motif in motifs[prot_name]:
motif_struct = pdb.select("resid %d to %d"%motifs[prot_name][motif])
writePDB("%s.pdb"%urllib.quote(motif, safe=""),motif_struct)
print motif, sorted(list(set(motif_struct.getResnums())))
